000268890 001__ 268890 000268890 005__ 20240923164113.0 000268890 037__ $$aDZNE-2024-00389 000268890 1001_ $$0P:(DE-HGF)0$$aCampbell, Alexander$$b0 000268890 1112_ $$aMedical Imaging with Deep Learning$$cNashville, Tenn.$$d2023-07-10 - 2023-07-12$$gMIDL 2023$$wUSA 000268890 245__ $$aDBGDGM: Dynamic Brain Graph Deep Generative Model 000268890 260__ $$c2024 000268890 300__ $$a1346 - 1371 000268890 3367_ $$2ORCID$$aCONFERENCE_PAPER 000268890 3367_ $$033$$2EndNote$$aConference Paper 000268890 3367_ $$2BibTeX$$aINPROCEEDINGS 000268890 3367_ $$2DRIVER$$aconferenceObject 000268890 3367_ $$2DataCite$$aOutput Types/Conference Paper 000268890 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1727078219_3424 000268890 4900_ $$v227 000268890 500__ $$aISSN 2640-3498: Proceedings of Machine Learning Research 000268890 520__ $$aGraphs are a natural representation of brain activity derived from functional magnetic imaging (fMRI) data. It is well known that clusters of anatomical brain regions, known as functional connectivity networks (FCNs), encode temporal relationships which can serve as useful biomarkers for understanding brain function and dysfunction. Previous works, however, ignore the temporal dynamics of the brain and focus on static graphs. In this paper, we propose a dynamic brain graph deep generative model (DBGDGM) which simultaneously clusters brain regions into temporally evolving communities and learns dynamic unsupervised node embeddings. Specifically, DBGDGM represents brain graph nodes as embeddings sampled from a distribution over communities that evolve over time. We parameterise this community distribution using neural networks that learn from subject and node embeddings as well as past community assignments. Experiments demonstrate DBGDGM outperforms baselines in graph generation, dynamic link prediction, and is comparable for graph classification. Finally, an analysis of the learnt community distributions reveals overlap with known FCNs reported in neuroscience literature. 000268890 536__ $$0G:(DE-HGF)POF4-354$$a354 - Disease Prevention and Healthy Aging (POF4-354)$$cPOF4-354$$fPOF IV$$x0 000268890 7001_ $$0P:(DE-2719)9002679$$aSpasov, Simeon$$b1$$udzne 000268890 7001_ $$0P:(DE-HGF)0$$aToschi, Nicola$$b2 000268890 7001_ $$0P:(DE-HGF)0$$aLio, Pietro$$b3 000268890 773__ $$p1346-1371$$v227$$y2024 000268890 8564_ $$uhttps://proceedings.mlr.press/v227/campbell24b.html 000268890 8564_ $$uhttps://pub.dzne.de/record/268890/files/DZNE-2024-00389.pdf$$yOpenAccess 000268890 8564_ $$uhttps://pub.dzne.de/record/268890/files/DZNE-2024-00389.pdf?subformat=pdfa$$xpdfa$$yOpenAccess 000268890 909CO $$ooai:pub.dzne.de:268890$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery 000268890 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9002679$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b1$$kDZNE 000268890 9131_ $$0G:(DE-HGF)POF4-354$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vDisease Prevention and Healthy Aging$$x0 000268890 9141_ $$y2024 000268890 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess 000268890 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0 000268890 9201_ $$0I:(DE-2719)1013030$$kAG Mukherjee$$lStatistics and Machine Learning$$x0 000268890 980__ $$acontrib 000268890 980__ $$aVDB 000268890 980__ $$aUNRESTRICTED 000268890 980__ $$aI:(DE-2719)1013030 000268890 9801_ $$aFullTexts